sle2023/paper09

SLE 2023 paper:
GPT-3-Powered Type Error Debugging: Investigating the Use of Large Language Models for Code Repair

Francisco Ribeiro, José Nuno Macedo, Kanae Tsushima, Rui Abreu, João Saraiva

• DOI: 10.1145/3623476.3623522
• T4G: AI-for-SLE
  • The paper investigates using large language models (GPT-3) to assist with type-error debugging and code repair in language tooling.
• T1B: Static Semantics
  • The target problems are type errors and their diagnosis, which are rooted in static semantics and type systems.
• T5H: Usability
  • The motivation is improving the usefulness of compiler feedback and reducing developer effort in debugging type errors.

---

The page is maintained by Dr. Vadim Zaytsev a.k.a. @grammarware. Last updated: June 2026.